Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    expressions related to giving voice to marginalized narratives and perspectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    voices and stories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mtrl
    -0.41
    ----</
    -0.38
     besk
    -0.37
    İstinadlar
    -0.36
    SequentialGroup
    -0.36
     AssemblyCompany
    -0.35
     teórico
    -0.34
    Kaynakça
    -0.34
    FXML
    -0.34
     Crime
    -0.34
    POSITIVE LOGITS
     ویکی‌پدی
    0.57
     يتيمه
    0.57
    Personensuche
    0.55
     voices
    0.49
     CommonModule
    0.47
     vérité
    0.46
     truths
    0.45
     truth
    0.43
    voices
    0.43
    Voices
    0.42
    Act Density 0.198%

    No Known Activations